Implementation notes: amd64, genji262, crypto_sign/dilithium4

Computer: genji262
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20191017
Operation: crypto_sign
Primitive: dilithium4

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1002056	231126 0 0	257811 816 1632	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1082642	236497 0 0	267028 864 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191024	20191017
1087174	236481 0 0	267012 864 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191024	20191017
1091090	236481 0 0	267012 864 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191024	20191017
1095974	236497 0 0	267028 864 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191024	20191017
1104950	245873 0 0	274708 864 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191024	20191017
1130536	250473 0 0	280604 864 1600	`avx2`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191024	20191017
1135838	251033 0 0	281164 864 1600	`avx2`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191024	20191017
1139974	251033 0 0	281164 864 1600	`avx2`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191024	20191017
1142438	250473 0 0	280604 864 1600	`avx2`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191024	20191017
1144242	260409 0 0	289300 864 1600	`avx2`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191024	20191017
1195260	131033 0 0	156331 816 1632	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1208790	247553 0 0	277684 864 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191024	20191017
1216490	247553 0 0	277684 864 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191024	20191017
1219438	247553 0 0	277684 864 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191024	20191017
1226148	247553 0 0	277684 864 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191024	20191017
1247642	262281 0 0	292444 864 1600	`avx2`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191024	20191017
1250964	262281 0 0	292444 864 1600	`avx2`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191024	20191017
1251888	262281 0 0	292444 864 1600	`avx2`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191024	20191017
1256882	262281 0 0	292444 864 1600	`avx2`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191024	20191017
1277848	126015 0 0	150331 808 1600	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1296834	128835 0 0	153883 816 1632	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
1988470	47849 0 0	74771 816 1632	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
2041094	37419 0 0	64545 808 1600	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
2194566	19547 0 0	45075 816 1632	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
2330856	67928 0 0	98732 864 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O2_-fomit-frame-pointer`	20191024	20191017
2332902	67928 0 0	98732 864 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O2_-fomit-frame-pointer`	20191024	20191017
2357058	70072 0 0	99252 864 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O3_-fomit-frame-pointer`	20191024	20191017
2366452	41557 0 0	68393 808 1600	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
2375604	72488 0 0	102892 864 1600	`ref`	`icc_-march=broadwell_-mtune=broadwell_-O3_-fomit-frame-pointer`	20191024	20191017
2377012	18232 0 0	43483 816 1632	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
2378354	72488 0 0	102892 864 1600	`ref`	`icc_-march=skylake_-mtune=skylake_-O3_-fomit-frame-pointer`	20191024	20191017
2379542	67912 0 0	98716 864 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O2_-fomit-frame-pointer`	20191024	20191017
2382358	67912 0 0	98716 864 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O2_-fomit-frame-pointer`	20191024	20191017
2467520	65792 0 0	94916 864 1600	`ref`	`icc_-march=corei7_-mtune=corei7_-O2_-fomit-frame-pointer`	20191024	20191017
2477970	72376 0 0	102780 864 1600	`ref`	`icc_-march=core-avx2_-mtune=core-avx2_-O3_-fomit-frame-pointer`	20191024	20191017
2485516	72376 0 0	102780 864 1600	`ref`	`icc_-march=haswell_-mtune=haswell_-O3_-fomit-frame-pointer`	20191024	20191017
2621960	29854 0 0	56417 808 1600	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
2629792	29854 0 0	56417 808 1600	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
2651572	17099 0 0	41259 808 1600	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20191024	20191017
2715350	18595 0 0	42583 800 1600	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20191024	20191017
2938298	67464 0 0	97884 864 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O2_-fomit-frame-pointer`	20191024	20191017
2940058	67464 0 0	97884 864 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O2_-fomit-frame-pointer`	20191024	20191017
2940168	67464 0 0	97884 864 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O2_-fomit-frame-pointer`	20191024	20191017
2942368	67464 0 0	97884 864 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O2_-fomit-frame-pointer`	20191024	20191017
3007136	71864 0 0	102316 864 1600	`ref`	`icc_-march=ivybridge_-mtune=ivybridge_-O3_-fomit-frame-pointer`	20191024	20191017
3011778	71864 0 0	102316 864 1600	`ref`	`icc_-march=sandybridge_-mtune=sandybridge_-O3_-fomit-frame-pointer`	20191024	20191017
3024230	71864 0 0	102316 864 1600	`ref`	`icc_-march=corei7-avx_-mtune=corei7-avx_-O3_-fomit-frame-pointer`	20191024	20191017
3024252	71864 0 0	102316 864 1600	`ref`	`icc_-march=core-avx-i_-mtune=core-avx-i_-O3_-fomit-frame-pointer`	20191024	20191017

Test failure

Implementation: avx2
Security model: unknown
Compiler: icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 12, namely:

Compiler	Implementations
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	avx2
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	avx2
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	avx2
icc -march=cannonlake -mtune=cannonlake -O2 -fomit-frame-pointer	ref
icc -march=cannonlake -mtune=cannonlake -O3 -fomit-frame-pointer	ref
icc -march=icelake-client -mtune=icelake-client -O2 -fomit-frame-pointer	ref
icc -march=icelake-client -mtune=icelake-client -O3 -fomit-frame-pointer	ref
icc -march=skylake-avx512 -mtune=skylake-avx512 -O2 -fomit-frame-pointer	ref
icc -march=skylake-avx512 -mtune=skylake-avx512 -O3 -fomit-frame-pointer	ref

Compiler output

Implementation: avx2
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:19:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/smmintrin.h:32:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/tmmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/pmmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/emmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: In file included from /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/xmmintrin.h:31:
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:55:72: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:61:72: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline void __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:68:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:74:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:84:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:90:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: /software/compilers/gcc/gcc-9.2.0-full+isl+binutils/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include/mmintrin.h:97:74: warning: unknown attribute '__artificial__' ignored [-Wunknown-attributes]
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2